def load_and_cache_examples(args, tokenizer, evaluate=False): processor = DataProcessor() # Load data features from cache or dataset file cached_features_file = os.path.join(args.cache_dir, 'cached_{}_{}_{}'.format( 'dev' if evaluate else 'train', list(filter(None, args.model_name_or_path.split('/'))).pop(), str(args.max_seq_length))) if os.path.exists(cached_features_file): logger.info("Loading features from cached file %s", cached_features_file) features = torch.load(cached_features_file) else: logger.info("Creating features from dataset file at %s", args.data_dir) label_list = processor.get_labels() examples = processor.get_dev_examples(args.data_dir) if evaluate else processor.get_train_examples(args.data_dir) features = convert_examples_to_features(examples, label_list, args.max_seq_length, tokenizer, cls_token_at_end=bool(args.model_type in ['xlnet']), # xlnet has a cls token at the end cls_token=tokenizer.cls_token, sep_token=tokenizer.sep_token, cls_token_segment_id=2 if args.model_type in ['xlnet'] else 0, pad_on_left=bool(args.model_type in ['xlnet']), # pad on the left for xlnet pad_token_segment_id=4 if args.model_type in ['xlnet'] else 0) if args.local_rank in [-1, 0]: logger.info("Saving features into cached file %s", cached_features_file) torch.save(features, cached_features_file) # Convert to Tensors and build dataset all_input_ids = torch.tensor([f.input_ids for f in features], dtype=torch.long) all_input_mask = torch.tensor([f.input_mask for f in features], dtype=torch.long) all_segment_ids = torch.tensor([f.segment_ids for f in features], dtype=torch.long) all_label_ids = torch.tensor([f.label_id for f in features], dtype=torch.long) dataset = TensorDataset(all_input_ids, all_input_mask, all_segment_ids, all_label_ids) return dataset
def main(): parser = argparse.ArgumentParser() ## Required parameters parser.add_argument("--data_dir", default=None, type=str, required=True, help="The input data dir. Should contain the .tsv files (or other data files) for the task.") parser.add_argument("--model_type", default=None, type=str, required=True, help="Model type selected in the list: " + ", ".join(MODEL_CLASSES.keys())) parser.add_argument("--model_name_or_path", default=None, type=str, required=True, help="Path to pre-trained model or shortcut name selected in the list: " + ", ".join(ALL_MODELS)) parser.add_argument("--output_dir", default=None, type=str, required=True, help="The output directory where the model predictions and checkpoints will be written.") ## Other parameters parser.add_argument("--config_name", default="", type=str, help="Pretrained config name or path if not the same as model_name") parser.add_argument("--tokenizer_name", default="", type=str, help="Pretrained tokenizer name or path if not the same as model_name") parser.add_argument("--cache_dir", default="", type=str, help="Where do you want to store the pre-trained models downloaded from s3") parser.add_argument("--max_seq_length", default=128, type=int, help="The maximum total input sequence length after tokenization. Sequences longer " "than this will be truncated, sequences shorter will be padded.") parser.add_argument("--do_train", action='store_true', help="Whether to run training.") parser.add_argument("--do_eval", action='store_true', help="Whether to run eval on the dev set.") parser.add_argument("--evaluate_during_training", action='store_true', help="Rul evaluation during training at each logging step.") parser.add_argument("--do_lower_case", action='store_true', help="Set this flag if you are using an uncased model.") parser.add_argument("--per_gpu_train_batch_size", default=8, type=int, help="Batch size per GPU/CPU for training.") parser.add_argument("--per_gpu_eval_batch_size", default=8, type=int, help="Batch size per GPU/CPU for evaluation.") parser.add_argument('--gradient_accumulation_steps', type=int, default=1, help="Number of updates steps to accumulate before performing a backward/update pass.") parser.add_argument("--learning_rate", default=5e-5, type=float, help="The initial learning rate for Adam.") parser.add_argument("--weight_decay", default=0.0, type=float, help="Weight deay if we apply some.") parser.add_argument("--adam_epsilon", default=1e-8, type=float, help="Epsilon for Adam optimizer.") parser.add_argument("--max_grad_norm", default=1.0, type=float, help="Max gradient norm.") parser.add_argument("--num_train_epochs", default=3.0, type=float, help="Total number of training epochs to perform.") parser.add_argument("--max_steps", default=-1, type=int, help="If > 0: set total number of training steps to perform. Override num_train_epochs.") parser.add_argument("--warmup_steps", default=0, type=int, help="Linear warmup over warmup_steps.") parser.add_argument('--logging_steps', type=int, default=50, help="Log every X updates steps.") parser.add_argument('--save_steps', type=int, default=50, help="Save checkpoint every X updates steps.") parser.add_argument("--eval_all_checkpoints", action='store_true', help="Evaluate all checkpoints starting with the same prefix as model_name ending and ending with step number") parser.add_argument("--no_cuda", action='store_true', help="Avoid using CUDA when available") parser.add_argument('--overwrite_output_dir', action='store_true', help="Overwrite the content of the output directory") parser.add_argument('--overwrite_cache', action='store_true', help="Overwrite the cached training and evaluation sets") parser.add_argument('--seed', type=int, default=42, help="random seed for initialization") parser.add_argument('--fp16', action='store_true', help="Whether to use 16-bit (mixed) precision (through NVIDIA apex) instead of 32-bit") parser.add_argument('--fp16_opt_level', type=str, default='O1', help="For fp16: Apex AMP optimization level selected in ['O0', 'O1', 'O2', and 'O3']." "See details at https://nvidia.github.io/apex/amp.html") parser.add_argument("--local_rank", type=int, default=-1, help="For distributed training: local_rank") parser.add_argument('--server_ip', type=str, default='', help="For distant debugging.") parser.add_argument('--server_port', type=str, default='', help="For distant debugging.") args = parser.parse_args() if os.path.exists(args.output_dir) and os.listdir(args.output_dir) and args.do_train and not args.overwrite_output_dir: raise ValueError("Output directory ({}) already exists and is not empty. Use --overwrite_output_dir to overcome.".format(args.output_dir)) # Setup distant debugging if needed if args.server_ip and args.server_port: # Distant debugging - see https://code.visualstudio.com/docs/python/debugging#_attach-to-a-local-script import ptvsd print("Waiting for debugger attach") ptvsd.enable_attach(address=(args.server_ip, args.server_port), redirect_output=True) ptvsd.wait_for_attach() # Setup CUDA, GPU & distributed training if args.local_rank == -1 or args.no_cuda: device = torch.device("cuda" if torch.cuda.is_available() and not args.no_cuda else "cpu") args.n_gpu = torch.cuda.device_count() else: # Initializes the distributed backend which will take care of sychronizing nodes/GPUs torch.cuda.set_device(args.local_rank) device = torch.device("cuda", args.local_rank) torch.distributed.init_process_group(backend='nccl') args.n_gpu = 1 args.device = device # Setup logging logging.basicConfig(format = '%(asctime)s - %(levelname)s - %(name)s - %(message)s', datefmt = '%m/%d/%Y %H:%M:%S', level = logging.INFO if args.local_rank in [-1, 0] else logging.WARN) logger.warning("Process rank: %s, device: %s, n_gpu: %s, distributed training: %s, 16-bits training: %s", args.local_rank, device, args.n_gpu, bool(args.local_rank != -1), args.fp16) # Set seed set_seed(args) # Prepare task processor = DataProcessor() label_list = processor.get_labels() num_labels = len(label_list) # Load pretrained model and tokenizer if args.local_rank not in [-1, 0]: torch.distributed.barrier() # Make sure only the first process in distributed training will download model & vocab config_class, model_class, tokenizer_class = MODEL_CLASSES[args.model_type] config = config_class.from_pretrained(args.config_name if args.config_name else args.model_name_or_path, num_labels=num_labels, finetuning_task='almond-frontend') tokenizer = tokenizer_class.from_pretrained(args.tokenizer_name if args.tokenizer_name else args.model_name_or_path, do_lower_case=args.do_lower_case) model = model_class.from_pretrained(args.model_name_or_path, from_tf=bool('.ckpt' in args.model_name_or_path), config=config) if args.local_rank == 0: torch.distributed.barrier() # Make sure only the first process in distributed training will download model & vocab model.to(args.device) if args.n_gpu > 1: model = torch.nn.DataParallel(model) logger.info("Training/evaluation parameters %s", args) # Training if args.do_train: train_dataset = load_and_cache_examples(args, tokenizer, evaluate=False) global_step, tr_loss = train(args, train_dataset, model, tokenizer) logger.info(" global_step = %s, average loss = %s", global_step, tr_loss) # Saving best-practices: if you use defaults names for the model, you can reload it using from_pretrained() if args.do_train and (args.local_rank == -1 or torch.distributed.get_rank() == 0): # Create output directory if needed if not os.path.exists(args.output_dir) and args.local_rank in [-1, 0]: os.makedirs(args.output_dir) logger.info("Saving model checkpoint to %s", args.output_dir) # Save a trained model, configuration and tokenizer using `save_pretrained()`. # They can then be reloaded using `from_pretrained()` model_to_save = model.module if hasattr(model, 'module') else model # Take care of distributed/parallel training model_to_save.save_pretrained(args.output_dir) tokenizer.save_pretrained(args.output_dir) # Good practice: save your training arguments together with the trained model torch.save(args, os.path.join(args.output_dir, 'training_args.bin')) # Load a trained model and vocabulary that you have fine-tuned model = model_class.from_pretrained(args.output_dir) tokenizer = tokenizer_class.from_pretrained(args.output_dir) model.to(args.device) # Evaluation results = {} if args.do_eval and args.local_rank in [-1, 0]: checkpoints = [args.output_dir] if args.eval_all_checkpoints: checkpoints = list(os.path.dirname(c) for c in sorted(glob.glob(args.output_dir + '/**/' + WEIGHTS_NAME, recursive=True))) logging.getLogger("pytorch_transformers.modeling_utils").setLevel(logging.WARN) # Reduce logging logger.info("Evaluate the following checkpoints: %s", checkpoints) for checkpoint in checkpoints: global_step = checkpoint.split('-')[-1] if len(checkpoints) > 1 else "" model = model_class.from_pretrained(checkpoint) model.to(args.device) result = evaluate(args, model, tokenizer, prefix=global_step) result = dict((k + '_{}'.format(global_step), v) for k, v in result.items()) results.update(result) return results